X-Git-Url: https://git.donarmstrong.com/?a=blobdiff_plain;f=unifracunweightedcommand.cpp;h=a50d147de23d7cbc882be909e4a78870a867d4c3;hb=a98eb683e17d8e49583bf2d215ab7562a4cdca75;hp=01f6f98fceb7349fdaf9ccdce53afdf60aaff42c;hpb=74844a60d80c6dd06e3fb02ee9b928424f9019b0;p=mothur.git diff --git a/unifracunweightedcommand.cpp b/unifracunweightedcommand.cpp index 01f6f98..a50d147 100644 --- a/unifracunweightedcommand.cpp +++ b/unifracunweightedcommand.cpp @@ -21,7 +21,7 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { else { //valid paramters for this command - string Array[] = {"groups","iters","distance","random", "outputdir","inputdir"}; + string Array[] = {"groups","iters","distance","random", "processors","outputdir","inputdir"}; vector myArray (Array, Array+(sizeof(Array)/sizeof(string))); OptionParser parser(option); @@ -40,7 +40,7 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { //if the user changes the output directory command factory will send this info to us in the output parameter outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; - outputDir += hasPath(globaldata->inputFileName); //if user entered a file with a path then preserve it + outputDir += m->hasPath(globaldata->inputFileName); //if user entered a file with a path then preserve it } //check for optional parameter and set defaults @@ -48,7 +48,7 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { groups = validParameter.validFile(parameters, "groups", false); if (groups == "not found") { groups = ""; } else { - splitAtDash(groups, Groups); + m->splitAtDash(groups, Groups); globaldata->Groups = Groups; } @@ -56,26 +56,29 @@ UnifracUnweightedCommand::UnifracUnweightedCommand(string option) { convert(itersString, iters); string temp = validParameter.validFile(parameters, "distance", false); if (temp == "not found") { temp = "false"; } - phylip = isTrue(temp); + phylip = m->isTrue(temp); - temp = validParameter.validFile(parameters, "random", false); if (temp == "not found") { temp = "true"; } - random = isTrue(temp); + temp = validParameter.validFile(parameters, "random", false); if (temp == "not found") { temp = "f"; } + random = m->isTrue(temp); + + temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = "1"; } + convert(temp, processors); if (!random) { iters = 0; } //turn off random calcs //if user selects distance = true and no groups it won't calc the pairwise if ((phylip) && (Groups.size() == 0)) { groups = "all"; - splitAtDash(groups, Groups); + m->splitAtDash(groups, Groups); globaldata->Groups = Groups; } if (abort == false) { T = globaldata->gTree; tmap = globaldata->gTreemap; - sumFile = outputDir + getSimpleName(globaldata->getTreeFile()) + ".uwsummary"; + sumFile = outputDir + m->getSimpleName(globaldata->getTreeFile()) + ".uwsummary"; outputNames.push_back(sumFile); - openOutputFile(sumFile, outSum); + m->openOutputFile(sumFile, outSum); util = new SharedUtil(); util->setGroups(globaldata->Groups, tmap->namesOfGroups, allGroups, numGroups, "unweighted"); //sets the groups the user wants to analyze @@ -105,7 +108,7 @@ void UnifracUnweightedCommand::help(){ m->mothurOut("The groups parameter allows you to specify which of the groups in your groupfile you would like analyzed. You must enter at least 1 valid group.\n"); m->mothurOut("The group names are separated by dashes. The iters parameter allows you to specify how many random trees you would like compared to your tree.\n"); m->mothurOut("The distance parameter allows you to create a distance file from the results. The default is false.\n"); - m->mothurOut("The random parameter allows you to shut off the comparison to random trees. The default is true, meaning compare your trees with randomly generated trees.\n"); + m->mothurOut("The random parameter allows you to shut off the comparison to random trees. The default is false, meaning compare don't your trees with randomly generated trees.\n"); m->mothurOut("The unifrac.unweighted command should be in the following format: unifrac.unweighted(groups=yourGroups, iters=yourIters).\n"); m->mothurOut("Example unifrac.unweighted(groups=A-B-C, iters=500).\n"); m->mothurOut("The default value for groups is all the groups in your groupfile, and iters is 1000.\n"); @@ -125,6 +128,8 @@ int UnifracUnweightedCommand::execute() { if (abort == true) { return 0; } + int start = time(NULL); + userData.resize(numComp,0); //data[0] = unweightedscore randomData.resize(numComp,0); //data[0] = unweightedscore //create new tree with same num nodes and leaves as users @@ -134,20 +139,29 @@ int UnifracUnweightedCommand::execute() { //get pscores for users trees for (int i = 0; i < T.size(); i++) { + if (m->control_pressed) { + outSum.close(); + for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } + return 0; + } + counter = 0; if (random) { - output = new ColumnFile(outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted", itersString); - outputNames.push_back(outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted"); + output = new ColumnFile(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted", itersString); + outputNames.push_back(outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted"); } + //get unweighted for users tree rscoreFreq.resize(numComp); rCumul.resize(numComp); utreeScores.resize(numComp); UWScoreSig.resize(numComp); - userData = unweighted->getValues(T[i]); //userData[0] = unweightedscore + userData = unweighted->getValues(T[i], processors, outputDir); //userData[0] = unweightedscore + + if (m->control_pressed) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); }return 0; } //output scores for each combination for(int k = 0; k < numComp; k++) { @@ -157,11 +171,14 @@ int UnifracUnweightedCommand::execute() { //add users score to validscores validScores[userData[k]] = userData[k]; } - - //get unweighted scores for random trees + + //get unweighted scores for random trees - if random is false iters = 0 for (int j = 0; j < iters; j++) { + //we need a different getValues because when we swap the labels we only want to swap those in each pairwise comparison - randomData = unweighted->getValues(T[i], "", ""); + randomData = unweighted->getValues(T[i], "", "", processors, outputDir); + + if (m->control_pressed) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } for(int k = 0; k < numComp; k++) { //add trees unweighted score to map of scores @@ -175,24 +192,31 @@ int UnifracUnweightedCommand::execute() { //add randoms score to validscores validScores[randomData[k]] = randomData[k]; } + + //report progress + m->mothurOut("Iter: " + toString(j+1)); m->mothurOutEndLine(); } - + for(int a = 0; a < numComp; a++) { float rcumul = 1.0000; - //this loop fills the cumulative maps and put 0.0000 in the score freq map to make it easier to print. - for (map::iterator it = validScores.begin(); it != validScores.end(); it++) { - //make rscoreFreq map and rCumul - map::iterator it2 = rscoreFreq[a].find(it->first); - rCumul[a][it->first] = rcumul; - //get percentage of random trees with that info - if (it2 != rscoreFreq[a].end()) { rscoreFreq[a][it->first] /= iters; rcumul-= it2->second; } - else { rscoreFreq[a][it->first] = 0.0000; } //no random trees with that score - } - if (random) { UWScoreSig[a].push_back(rCumul[a][userData[a]]); } - else { UWScoreSig[a].push_back(0.0); } + if (random) { + //this loop fills the cumulative maps and put 0.0000 in the score freq map to make it easier to print. + for (map::iterator it = validScores.begin(); it != validScores.end(); it++) { + //make rscoreFreq map and rCumul + map::iterator it2 = rscoreFreq[a].find(it->first); + rCumul[a][it->first] = rcumul; + //get percentage of random trees with that info + if (it2 != rscoreFreq[a].end()) { rscoreFreq[a][it->first] /= iters; rcumul-= it2->second; } + else { rscoreFreq[a][it->first] = 0.0000; } //no random trees with that score + } + UWScoreSig[a].push_back(rCumul[a][userData[a]]); + }else { UWScoreSig[a].push_back(0.0); } + } - + + if (m->control_pressed) { if (random) { delete output; } outSum.close(); for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + //print output files printUWSummaryFile(i); if (random) { printUnweightedFile(); delete output; } @@ -205,10 +229,13 @@ int UnifracUnweightedCommand::execute() { UWScoreSig.clear(); } - //reset groups parameter - globaldata->Groups.clear(); + outSum.close(); + if (m->control_pressed) { for (int i = 0; i < outputNames.size(); i++) { remove(outputNames[i].c_str()); } return 0; } + + m->mothurOut("It took " + toString(time(NULL) - start) + " secs to run unifrac.unweighted."); m->mothurOutEndLine(); + m->mothurOutEndLine(); m->mothurOut("Output File Names: "); m->mothurOutEndLine(); for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); } @@ -265,16 +292,16 @@ void UnifracUnweightedCommand::printUWSummaryFile(int i) { if (UWScoreSig[a][0] > (1/(float)iters)) { outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << UWScoreSig[a][0] << endl; cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << UWScoreSig[a][0] << endl; - m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t" + toString(UWScoreSig[a][0])); m->mothurOutEndLine(); + m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t" + toString(UWScoreSig[a][0])+ "\n"); }else { outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl; cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << setprecision(itersString.length()) << "<" << (1/float(iters)) << endl; - m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t<" + toString((1/float(iters)))); m->mothurOutEndLine(); + m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t<" + toString((1/float(iters))) + "\n"); } }else{ outSum << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << "0.00" << endl; cout << setprecision(6) << groupComb[a] << '\t' << utreeScores[a][0] << '\t' << "0.00" << endl; - m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t0.00"); m->mothurOutEndLine(); + m->mothurOutJustToLog(groupComb[a] + "\t" + toString(utreeScores[a][0]) + "\t0.00\n"); } } @@ -287,11 +314,11 @@ void UnifracUnweightedCommand::printUWSummaryFile(int i) { /***********************************************************/ void UnifracUnweightedCommand::createPhylipFile(int i) { try { - string phylipFileName = outputDir + getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.dist"; + string phylipFileName = outputDir + m->getSimpleName(globaldata->getTreeFile()) + toString(i+1) + ".unweighted.dist"; outputNames.push_back(phylipFileName); ofstream out; - openOutputFile(phylipFileName, out); + m->openOutputFile(phylipFileName, out); //output numSeqs out << globaldata->Groups.size() << endl; @@ -306,8 +333,8 @@ void UnifracUnweightedCommand::createPhylipFile(int i) { int count = 0; for (int r=0; rGroups.size(); r++) { for (int l = r+1; l < globaldata->Groups.size(); l++) { - dists[r][l] = (1.0 - utreeScores[count][0]); - dists[l][r] = (1.0 - utreeScores[count][0]); + dists[r][l] = utreeScores[count][0]; + dists[l][r] = utreeScores[count][0]; count++; } }